See how Xurmo
enables better
decision making.

BUSINESS CHALLENGE

The client was able to predict demand at a distributor level with some level of success, but failed entirely to predict demand at a retailer level. They also wanted to include data points from social media for the analysis.

XURMO SOLUTION

Using Xurmo, they were able to extract data from their existing systems, from Twitter and from news, sports and weather related websites. Using the Machine Learning algorithms available in Xurmo, various models were created, and they were then able to use data points from these different sources to build a demand prediction model that was able to predict the demand at a SKU level for a particular retailer more accurately.

BUSINESS IMPACT

Out-of-Stock situations were reduced by 50%

BUSINESS CHALLENGE

A large insurance provider wanted to cluster customers into unique segments and then to identify within those segments, which customers were likely to churn.

XURMO SOLUTION

The solution involved the Clustering, Classification and Visualization modules of Xurmo. We created a clustering model that allowed our customer to segregate their clientele into eight distinct segments. Classification was used to create a model that could predict with a certain probability estimate as to whether a customer would churn or not. Once the models were created, they were tied to visualizations and presented as an end user application (Dashboard) for the Client's Analysts.

BUSINESS IMPACT

Lowered rate of churn by 20%

Enabled pre-emptive measures to be implemented to prevent a customer churning

BUSINESS CHALLENGE

The requirement for this Bank was to provide a single view of all product recommendations to each of the 28 million customers based on structured (existing EDW) and unstructured data (CRM and Emails). The target was to reduce the processing time for product recommendations from the current more than three weeks to less than a day.

XURMO SOLUTION

The lengthy SAS Scorecards were easily translated using the Xurmo interactive query language. The translated Scorecards now run efficiently on a distributed environment . The various Scorecards are tied to a simple application interface built on the Platform to generate the Single Customer View at the click of a button.

BUSINESS IMPACT

Xurmo achieved the performance target of less than a day

Provided a highly scalable solution that run on commodity servers rather than requiring expensive large enterprise class servers

BUSINESS CHALLENGE

A financial institution wanted to use industry news to tweak their stock prediction models. Using Xurmo's HTML Connector, they were able to extract relevant news articles about the various stocks that they were tracking. They then used Xurmo's Machine Learning algorithms to create a custom sentiment analyser to predict the sentiment of a news point with respect to a particular company.

BUSINESS IMPACT

In six days, the client was able to use their existing data points along with the industry sentiment information to create a new stock price movement model with higher accuracy

BUSINESS CHALLENGE

A customer in the KPO industry was having trouble managing the information that was being generated by their analysts. Insights gleaned by analysts via their experiences weren't being captured, documents pertaining to projects were stored on individual analysts systems, and there was loss of information due to employee churn. The problems caused by these information silos were enhanced by the global operations of the client.

XURMO SOLUTION

Using INSIGHT, a Knowledge Discovery application built on Xurmo, the client was able to remove the barriers to the information. Insight was able to parse emails, chats, documents from both local machines and CMS systems, and other Meta data to be able to recommend the People, Documents and Conversations that could answer a user's query.

BUSINESS IMPACT

Analysts were more efficient,thus reducing costs and turnaround times for projects by 60%

BUSINESS CHALLENGE

An Oil and Gas major wanted to derive intelligence about their oil production. They also wanted to track the various deals going on in this domain.

XURMO SOLUTION

Using Xurmo's Connectors, they fed information about the different Oil refineries and Gas plants, articles coming from a set of defined industry sources and information about sales, operation costs etc. into Xurmo. All this data was then consolidated and presented in a customized dashboard to the client.

BUSINESS IMPACT

80% reduction in information gathering time

Holistic view of oil production

BUSINESS CHALLENGE

A Global Media House was having very poor responses to their email marketing campaigns. To overcome this, the client wanted to personalize the email subject lines in order to be more relevant to the user. They wanted to be able to predict which product and in turn what subject line for that product, a customer would be more likely to respond to.

XURMO SOLUTION

To do this, they used the Machine Learning algorithms of Xurmo to analyse previous purchasing behaviour of all their customers to come up with a model that accurately predicted which email subject lines (for a particular product) fit which user profile. It took only few days to build and deploy the model in an end user application.

BUSINESS IMPACT

A 10% increase in the number or responses to their emails

BUSINESS CHALLENGE

A Global Pharmaceutical company wanted to analyse publically available information to gain insights about how their drugs were being accepted.

XURMO SOLUTION

Using Xurmo's HTML connector they able to extract comments about a particular drug from different Internet forums. As a comment could possibly belong to more than one category of information, they split the comments into sentences. They then built a model that predicted whether a sentence belonged to one of four categories using the Classification Module of Xurmo. They also used Xurmo's proprietary Sentiment model to classify each sentence into a particular sentiment. This enhanced data set was then fed into an application that could show comments broken down by drug, category and sentiment.

BUSINESS IMPACT

Feedback cycles were reduced by 70%

BUSINESS CHALLENGE

Data pertaining to quality checks at each stage of the manufacturing process for a particular product of the client was stored in a series of Excel files, maintained individually by each of the manufacturing factories. This meant that data sanctity was nonexistent, manufacturing specifications weren't being met and the analysis process (while not complex) was tedious as it meant that these files would have to be transferred into a predefined format, collated, cleaned and then processed for various insights

XURMO SOLUTION

Due to these problems the client wanted to setup a system that would simply, standardize and enforce specifications for data entry & automate the BI requirements of the management teams. Using Xurmo they were able to implement a system to do this resulting in better quality, reduced waste and increased accountability.

BUSINESS IMPACT

Quality problems were detected in (near) real time

Reporting became automated

BUSINESS CHALLENGE

The Client also wished to create new products that could take advantage of the social media revolution but were restricted by the inherent limitations of their existing data warehouse setup.

XURMO SOLUTION

The Xurmo Platform allowed customer data whether it came from Facebook, Twitter, CSV or RDBMS to be loaded via scheduled Connectors that easily handled large & incremental amounts of data. The Fabric DB could store the data without any schema setup irrespective of origin or structure of the data. The processing logic was quickly created on Xurmo's workflow module to incorporate insights from various social media sources. Xurmo's Advanced Analytic modules enabled the Client to create better Member Matching models that related member information from social sites to their loyalty programs, that lasted longer and which could take user feedback to become better.

BUSINESS IMPACT

Deeper insights into customers lead to more personalized offers and in turn a 20% increase in offer conversion

BUSINESS CHALLENGE

The client wanted to be able to categorize comments made by users in their support forum into one of about 6,000 categories across five levels automatically.

XURMO SOLUTION

Using Xurmo's Text Analytics and Machine Learning Suites the client was able to apply these operations, build models for various hypotheses, and quickly test them. To automatically classify the comments, text processing operations were required to break down the text into individual tokens, apply Feature Reduction to remove unnecessary words/phrases, and build a taxonomy. Along with this, machine learning algorithms were required to detect patterns in the volume of data.

BUSINESS IMPACT

A robust Machine Learning Model that could adapt to new patterns in the data

Insights from comments allowed the client to identify common flaws & their fixes for their products

BUSINESS CHALLENGE

The client wanted to be able to categorize comments made by users in their support forum into one of about 6,000 categories across five levels automatically.

XURMO SOLUTION

Using Xurmo's Text Analytics and Machine Learning Suites the client was able to apply these operations, build models for various hypotheses, and quickly test them. To automatically classify the comments, text processing operations were required to break down the text into individual tokens, apply Feature Reduction to remove unnecessary words/phrases, and build a taxonomy. Along with this, machine learning algorithms were required to detect patterns in the volume of data.

BUSINESS IMPACT

A robust Machine Learning Model that could adapt to new patterns in the data

Insights from comments allowed the client to identify common flaws & their fixes for their products